Download presentation
Presentation is loading. Please wait.
Published byJonah McDaniel Modified over 9 years ago
1
Supervised Learning of Edges and Object Boundaries Piotr Dollár Zhuowen Tu Serge Belongie
2
The problem
3
Outline I. Motivation II. Problem formulation III. Learning architecture ( BEL ) IV. Results
4
Outline I. Motivation –Why edges? –Why not edges? –Why learning? II. Problem formulation III. Learning architecture ( BEL ) IV. Results
5
Why edges? Reduce dimensionality of data Preserve content information Useful in applications such as: –object detection –structure from motion –tracking
6
Why not edges? But, not that useful, why? Difficulties: 1.Modeling assumptions 2.Parameters 3.Multiple sources of information (brightness, color, texture, …) 4.Real world conditions Is edge detection even well defined?
7
Canny edge detection 1. smooth 2. gradient 3. thresh, suppress, link Canny is optimal w.r.t. some model.
8
Canny edge detection 1. smooth 2. gradient 3. thresh, suppress, link And yet…
9
1.Modeling assumptions Step edges, junctions, etc. 2.Parameters Scales, threshold, etc. 3.Multiple sources of information Only handles brightness 4.Real world conditions Gaussian iid noise? Texture… Canny difficulties
10
1.Modeling assumptions Complex models, computationally prohibitive 2.Parameters Many, may use learning to help tune 3.Multiple sources of information Typically brightness, color, and texture cues 4.Real world conditions Aimed at real images Modern methods
11
Modern methods ( Pb ) Pb – Martin et al. PAMI04
12
1.Modeling assumptions minimal 2.Parameters none 3.Multiple sources of information Automatically incorporated 4.Real world conditions training data Why learning?
13
Outline I. Motivation II. Problem formulation III. Learning architecture ( BEL ) IV. Results
14
Problem formulation (general) image scene interpretation that can include spatial location and extent of objects, regions, object boundaries, curves, etc. 0/1 function that encodes spatial extent of a component of W Obtaining optimal or likely W or S W can be difficult. Let: We seek to learn this distribution directly from image data. To further reduce complexity, we can discard the absolute coordinates of S: where N(c) is the neighborhood of I centered at c.
15
Problem formulation (edges) image segmentation 1 on boundaries of segments, 0 elsewhere
16
Discriminative framework Sample positive and negative patches according to above: Given an image I and n interpretations W obtained by manual annotation, we can compute: Goal is to learn from human labeled images Finally train a classifier!
17
Edge point present in center? NOYES Discriminative framework
18
Outline I. Motivation II. Problem formulation III. Learning architecture ( BEL ) IV. Results
19
Learning architecture Large training set O(10 8 ) –but correlated –very variable data Want generic, efficient features –applicability to any domain –fast computation essential Boosting a natural choice
20
AdaBoost Taken from tutorial by Jiri Matas and Jan Sochman
21
Decision Stumps Weak learners: (where f is some feature of x)
22
AdaBoost (decision stumps)
23
Cascaded classifiers Minimize computation during testing Especially useful for skewed prior Viola-Jones face/pedestrian detection
24
Cascade (AdaBoost)
25
Probabilistic boosting trees Expected amount of computation decreases significantly Once a mistake is made, it cannot be undone Cascade also made problem easier! Ideally, splitting data creates two sub-problems each much easier than original…
26
Probabilistic boosting trees
27
Retain efficiency of cascades Add power when necessary Prone to overfitting Tree was necessary to obtain good results. … … …
28
Haar features: Feature response: (image response to green squares) – (image response to red squares) Applied to many ‘views’ of the data –grayscale, color, Gabor filter outputs, etc. –at many orientations, locations, etc Fast computation using integral images Hundreds of thousands of candidate features …
29
Outline I. Motivation II. Problem formulation III. Learning architecture ( BEL ) IV. Results –Gestalt laws –Natural images –Road detection –Object Boundaries
30
Results Boosted edge learning ( BEL ) Compare to method with best known performance ( Pb ), and also to Canny Comparison not quite fair… Pb – Martin et al. PAMI04
31
Gestalt laws Gestalt laws of perceptual organization –Symmetry, closure, parallelism, etc. –Govern how component parts are organized into overall patterns The “hard” part of edge detection What can and cannot be achieved in our framework?
32
Analogies A:B :: C : ?
33
Gestalt laws: parallelism
34
Gestalt laws: modal completion
35
Gestalt laws: alternate interpretation
36
Outline I. Motivation II. Problem formulation III. Learning architecture ( BEL ) IV. Results –Gestalt laws –Natural images –Road detection –Object Boundaries
37
Natural Images Berkeley Segmentation Dataset and Benchmark –Standard dataset for edge detection with 300 manually annotated images –Modern benchmark for comparing edge detection algorithms Notes: –Edge detection in natural images is hard –Possibly ill-defined problem –Evil but necessary comparison
38
Natural Images: results
40
image human BELPb Natural Images: probabilities
41
Outline I. Motivation II. Problem formulation III. Learning architecture ( BEL ) IV. Results –Gestalt laws –Natural images –Road detection –Object Boundaries
42
Road detection location of roads in scene 1 if pixel is on the road, 0 elsewhere Road detection is not edge detection But same learning architecture Ground truth obtained from map data
43
Road detection (training) (the 2 training images)
44
Road detection (testing) (the testing image) (`Winchester Dr.’ was not detected)
45
Outline I. Motivation II. Problem formulation III. Learning architecture ( BEL ) IV. Results –Gestalt laws –Natural images –Road detection –Object Boundaries
46
Object boundaries location and extent of object of interest 1 on boundaries of object, 0 elsewhere Must tune to specific ‘type’ of edge Algorithms that model edges not applicable Potentially most useful application
47
Object boundaries (context)
48
Object boundaries (training) …
49
Object boundaries (ground truth)
50
Object boundaries (Canny) F-score =.10
51
Object boundaries ( Pb ) F-score =.13
52
Object boundaries ( BEL ) F-score =.79
53
Algorithm roundup AccurateAdaptableFast Canny Pb BEL
54
Summary Define edges only in terms of labeled data, minimal modeling assumptions Minimize human effort in adapting algorithm to particular domain Fast, affordable edge detection for the masses!
55
Thank you!
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.